Figure 1 - uploaded by Luc R Dermaut
Content may be subject to copyright.
Different positions of the tracing paper on the digitizer tablet to check the consistency of the digitizer table.
Source publication
The aims of this investigation were to determine the errors involved in cephalometric landmark identification and to link these to the interpretation of treatment results. Fifty cephalograms were randomly selected from patient files and the following were determined. (i) Accuracy of the digitizer--single tracing digitized on five occasions on each...
Contexts in source publication
Context 1
... tracing with the four reference points and the 35 marked landmarks was placed on the tablet. For 10 different positions equally divided over the whole surface of the digitizer tablet (Figure 1), five series of measurements of the same tracing were made each time by the same investigator to determine possible differences in the input of the landmark co-ordinates on the different locations. Variability on each position and between the different positions was calculated by superimposition of each of the five readings using the reference points. ...
Citations
... After landmark detection, these digital programs automatically draw and calculate the angles and planes formed between these anatomic landmarks. Therefore, it has been reported that the reason for errors and inconsistency in computer-assisted digital cephalometry is the incorrect anatomic landmark identification [1,6,7]. The smaller the error in determining the landmarks during analysis, the smaller the error regarding angles or distance in an analysis system [7]. ...
... Therefore, it has been reported that the reason for errors and inconsistency in computer-assisted digital cephalometry is the incorrect anatomic landmark identification [1,6,7]. The smaller the error in determining the landmarks during analysis, the smaller the error regarding angles or distance in an analysis system [7]. For this reason, there have been attempts to fully automate landmark identification in cephalometric analysis and thus improve the accuracy of measurements and reduce errors due to clinician subjectivity [8]. ...
... In the review study by Leonardi et al., it was emphasized that landmark detection in automatic tracing contains a larger margin of error than manual tracing, and that the use of automatic tracing for clinical purposes is not reliable [12]. Unlike this view, there are also studies that say that artificial intelligence gives as accurate results as human observers in detecting landmarks [7,11,13]. ...
... 6 Such a laborious activity tends to generate significant intra-and interobserver errors. 7 One of the challenges associated with manual tracing is the inherent subjectivity in landmark identification. In addition, the accuracy of manual tracing is affected by several factors, which include overlapping of anatomical structures, low image quality, and interindividual anatomical variations. ...
Objectives
To evaluate the reliability and reproducibility of an artificial intelligence (AI) software in identifying cephalometric points on lateral cephalometric radiographs considering four settings of brightness and contrast.
Methods and materials
Brightness and contrast of 30 lateral cephalometric radiographs were adjusted into four different settings. Then, the control examiner (ECont), the calibrated examiner (ECal), and the CEFBOT AI software (AIs) each marked 19 cephalometric points on all radiographs. Reliability was assessed with a second analysis of the radiographs 15 days after the first one. Statistical significance was set at p < 0.05.
Results
Reliability of landmark identification was excellent for the human examiners and the AIs regardless of the type of brightness and contrast setting (mean intraclass correlation coefficient >0.89). When ECont and ECal were compared for reproducibility, there were more cephalometric points with significant differences on the x-axis of the image with the highest contrast and the lowest brightness, namely N(p = 0.033), S(p = 0.030), Po(p < 0.001), and Pog’(p = 0.012). Between ECont and AIs, there were more cephalometric points with significant differences on the image with the highest contrast and the lowest brightness, namely N(p = 0.034), Or(p = 0.048), Po(p < 0.001), A(p = 0.042), Pog’(p = 0.004), Ll(p = 0.005), Ul(p < 0.001), and Sn(p = 0.001).
Conclusions
While the reliability of the AIs for cephalometric landmark identification was rated as excellent, low brightness and high contrast seemed to affect its reproducibility. The experienced human examiner, on the other hand, did not show such faulty reproducibility; therefore, the AIs used in this study is an excellent auxiliary tool for cephalometric analysis, but still depends on human supervision to be clinically reliable.
... www.nature.com/scientificreports/ overlapped images reduce the accuracy and reliability of landmark identification, resulting in identification that highly depends on the examiner's experience and subjectivity 22,[31][32][33] . The present study aimed to develop a fully automatic PA cephalometric landmark identification system using a two-step landmark detection framework. ...
This study aimed to propose a fully automatic posteroanterior (PA) cephalometric landmark identification model using deep learning algorithms and compare its accuracy and reliability with those of expert human examiners. In total, 1032 PA cephalometric images were used for model training and validation. Two human expert examiners independently and manually identified 19 landmarks on 82 test set images. Similarly, the constructed artificial intelligence (AI) algorithm automatically identified the landmarks on the images. The mean radial error (MRE) and successful detection rate (SDR) were calculated to evaluate the performance of the model. The performance of the model was comparable with that of the examiners. The MRE of the model was 1.87 ± 1.53 mm, and the SDR was 34.7%, 67.5%, and 91.5% within error ranges of < 1.0, < 2.0, and < 4.0 mm, respectively. The sphenoid points and mastoid processes had the lowest MRE and highest SDR in auto-identification; the condyle points had the highest MRE and lowest SDR. Comparable with human examiners, the fully automatic PA cephalometric landmark identification model showed promising accuracy and reliability and can help clinicians perform cephalometric analysis more efficiently while saving time and effort. Future advancements in AI could further improve the model accuracy and efficiency.
... At present, the analysis of cephalometric images by human experts can be considered as gold standard [17]. Nevertheless, in spite of clear definitions for the landmarks, it must be assumed that even the evaluation by human experts can be prone to errors [8,10,21,34]. To achieve a high level of quality for our gold standard, a set of 50 different randomly selected cephalometric X-rays was compiled. ...
Purpose:
The aim of this investigation was to evaluate the accuracy of various skeletal and dental cephalometric parameters as produced by different commercial providers that make use of artificial intelligence (AI)-assisted automated cephalometric analysis and to compare their quality to a gold standard established by orthodontic experts.
Methods:
Twelve experienced orthodontic examiners pinpointed 15 radiographic landmarks on a total of 50 cephalometric X‑rays. The landmarks were used to generate 9 parameters for orthodontic treatment planning. The "humans' gold standard" was defined by calculating the median value of all 12 human assessments for each parameter, which in turn served as reference values for comparisons with results given by four different commercial providers of automated cephalometric analyses (DentaliQ.ortho [CellmatiQ GmbH, Hamburg, Germany], WebCeph [AssembleCircle Corp, Seongnam-si, Korea], AudaxCeph [Audax d.o.o., Ljubljana, Slovenia], CephX [Orca Dental AI, Herzliya, Israel]). Repeated measures analysis of variances (ANOVAs) were calculated and Bland-Altman plots were generated for comparisons.
Results:
The results of the repeated measures ANOVAs indicated significant differences between the commercial providers' predictions and the humans' gold standard for all nine investigated parameters. However, the pairwise comparisons also demonstrate that there were major differences among the four commercial providers. While there were no significant mean differences between the values of DentaliQ.ortho and the humans' gold standard, the predictions of AudaxCeph showed significant deviations in seven out of nine parameters. Also, the Bland-Altman plots demonstrate that a reduced precision of AI predictions must be expected especially for values attributed to the inclination of the incisors.
Conclusion:
Fully automated cephalometric analyses are promising in terms of timesaving and avoidance of individual human errors. At present, however, they should only be used under supervision of experienced clinicians.
... Furthermore, this measurement method is based on imprecise landmarks. The positions of the Kr' and Cd' points, which are respectively located on the coronoid and condyle tip, can vary a lot, especially on a round-ended bony structure, the top of which is not an exact point but rather a curved line [17]. The same goes for the Go' point that can be positioned anywhere on the lower border of the corpus of the mandible, posteriorly to the dental region. ...
Introduction:
The objective of this study was to compare the length ratios obtained on panoramic radiography and computed tomography (CT) to verify whether the former is adequate for diagnosing coronoid process hyperplasia.
Methods:
A case series of patients with coronoid process hyperplasia was investigated. Length ratios between the coronoid process and condyle were measured on panoramic radiographs by using the Levandoski method and on CT scans by using the methods described by Tavassol et al. and Stopa et al. The mean length ratios obtained using the three measurement methods were compared.
Results:
The mean length ratio measured with the Levandoski method was significantly lower than that measured with the method described by Stopa et al. (1.09 [0.09] vs. 1.21 [0.09]; P = 0.0001) and lower than that measured with the method described by Tavassol et al. (1.09 [0.09] vs. 1.34 [0.44]; P = 0.013).
Conclusion:
Panoramic measurement of the coronoid process by using the Levandoski method tended to underestimate the length ratio, emphasizing the importance of using a scanographic measurement method at the slightest doubt to confirm the diagnosis of coronoid process hyperplasia.
... 22 These overlapped images reduce the accuracy and reliability of landmark identi cation, resulting in identi cation that highly depends on the examiner's experience and subjectivity. 23,24 Furthermore, it may also affect the accuracy of landmark identi cation by AI. ...
This aimed to propose a fully automatic posteroanterior (PA) cephalometric landmark identification model using deep learning algorithms and evaluate its accuracy and reliability compared with those of expert human examiners. In total, 1,032 PA cephalometric images were used for model training and validation. Two human expert examiners independently and manually identified 19 landmarks on 82 test set images. Similarly, the constructed artificial intelligence (AI) algorithm automatically identified the landmarks on the images. The mean radial error (MRE) and successful detection rate (SDR) were calculated to evaluate the performance of the model. The performance of the model was comparable with that of the examiners. MRE of the model was 1.87 ± 1.53 mm, and SDR was 34.7%, 67.5%, and 91.5% within error ranges of < 1.0, < 2.0, and < 4.0 mm, respectively. The sphenoid points and mastoid processes had the lowest MRE and highest SDR in auto-identification; the condyle points had the highest MRE and lowest SDR. The fully automatic PA cephalometric landmark identification model showed promising accuracy and reliability, comparable with those of the examiners and can help clinicians perform cephalometric analysis more efficiently while saving time and effort. Future advancements in AI could further improve the model accuracy and efficiency.
... vertical and horizontal reference lines etc. However, the process of manual annotation is tedious, time-consuming and subjective [4]. Although cephalometric tracing is generally performed by trained orthodontists, several reports have raised concerns regarding significant inter-and intra-observer variabilities among them [5] due to their diverse training and experience backgrounds. ...
The accurate identification and precise localization of cephalometric landmarks enable the classification and quantification of anatomical abnormalities. The traditional way of marking cephalometric landmarks on lateral cephalograms is a monotonous and time-consuming job. Endeavours to develop automated landmark detection systems have persistently been made, however, they are inadequate for orthodontic applications due to unavailability of a reliable dataset. We proposed a new state-of-the-art dataset to facilitate the development of robust AI solutions for quantitative morphometric analysis. The dataset includes 1000 lateral cephalometric radiographs (LCRs) obtained from 7 different radiographic imaging devices with varying resolutions, making it the most diverse and comprehensive cephalometric dataset to date. The clinical experts of our team meticulously annotated each radiograph with 29 cephalometric landmarks, including the most significant soft tissue landmarks ever marked in any publicly available dataset. Additionally, our experts also labelled the cervical vertebral maturation (CVM) stage of the patient in a radiograph, making this dataset the first standard resource for CVM classification. We believe that this dataset will be instrumental in the development of reliable automated landmark detection frameworks for use in orthodontics and beyond.
... vertical and horizontal reference lines etc. However, the process of manual annotation is tedious, time-consuming and subjective [4]. Although cephalometric tracing is generally performed by trained orthodontists, several reports have raised concerns regarding significant inter-and intra-observer variabilities among them [5] due to their diverse training and experience backgrounds. ...
The accurate identification and precise localization of cephalometric landmarks enable the classification and quantification of anatomical abnormalities. The traditional way of marking cephalometric landmarks on lateral cephalograms is a monotonous and time-consuming job. Endeavours to develop automated landmark detection systems have persistently been made, however, they are inadequate for orthodontic applications due to unavailability of a reliable dataset. We proposed a new state-of-the-art dataset to facilitate the development of robust AI solutions for quantitative morphometric analysis. The dataset includes 1000 lateral cephalometric radiographs (LCRs) obtained from 7 different radiographic imaging devices with varying resolutions, making it the most diverse and comprehensive cephalometric dataset to date. The clinical experts of our team meticulously annotated each radiograph with 29 cephalometric landmarks, including the most significant soft tissue landmarks ever marked in any publicly available dataset. Additionally, our experts also labelled the cervical vertebral maturation (CVM) stage of the patient in a radiograph, making this dataset the first standard resource for CVM classification. We believe that this dataset will be instrumental in the development of reliable automated landmark detection frameworks for use in orthodontics and beyond.
... In clinical settings, the landmarks are usually traced out manually by professional orthodontists, which is a very timeconsuming [11] and unreliable approach to achieving reproducible results [12]. Moreover, several reports have also voiced concerns about the significant inter-and intra-observer variabilities among them [13] due to various training and experience backgrounds. ...
Quantitative cephalometric analysis is the most widely used clinical and research tool in modern orthodontics. Accurate localization of cephalometric landmarks enables the quantification and classification of anatomical abnormalities, however, the traditional manual way of marking these landmarks is a very tedious job. Endeavours have constantly been made to develop automated cephalometric landmark detection systems but they are inadequate for orthodontic applications. The fundamental reason for this is that the amount of publicly available datasets as well as the images provided for training in these datasets are insufficient for an AI model to perform well. To facilitate the development of robust AI solutions for morphometric analysis, we organise the CEPHA29 Automatic Cephalometric Landmark Detection Challenge in conjunction with IEEE International Symposium on Biomedical Imaging (ISBI 2023). In this context, we provide the largest known publicly available dataset, consisting of 1000 cephalometric X-ray images. We hope that our challenge will not only derive forward research and innovation in automatic cephalometric landmark identification but will also signal the beginning of a new era in the discipline.
... Furthermore, this measurement method is based on imprecise landmarks. The positions of the Kr' and Cd' points, which are respectively located on the coronoid and condyle tip, can vary a lot, especially on a round-ended bony structure, the top of which is not an exact point but rather a curved line [14]. The same goes for the Go' point that can be positioned anywhere on the lower border of the corpus of the mandible, posteriorly to the dental region. ...
Introduction: The objective of this study was to compare the length ratios obtained on panoramic radiography and computed tomography (CT) to verify whether the former is adequate for diagnosing coronoid process hyperplasia.
Methods: A case series of patients with coronoid process hyperplasia was investigated. Length ratios between the coronoid process and condyle were measured on panoramic radiographs by using the Levandoski method and on CT scans by using the methods described by Tavassol et al. and Stopa et al. The mean length ratios obtained using the three measurement methods were compared.
Results: The mean length ratio measured with the Levandoski method was significantly lower than that measured with the method described by Stopa et al. (1.09 [0.09] vs. 1.21 [0.09]; P = 0.0001) and lower than that measured with the method described by Tavassol et al. (1.09 [0.09] vs. 1.34 [0.44]; P = 0.013).
Conclusion: Panoramic measurement of the coronoid process by using the Levandoski method tended to underestimate the length ratio, emphasizing the importance of using a scanographic measurement method at the slightest doubt to confirm the diagnosis of coronoid process hyperplasia.
